• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2010.11a
• /
• pp.671-672
• /
• 2010

• Smart Structures and Systems
• /
• v.30 no.6
• /
• pp.583-599
• /
• 2022

In this paper, a multi-objective wireless sensor network configuration optimization method is proposed. The proposed method aims to determine the optimal information and lifespan wireless sensor network for structural health monitoring of large-scale infrastructures. In particular, cluster-based wireless sensor networks with multi-type of sensors are considered. To optimize the lifetime of the wireless sensor network, a cluster-based network optimization algorithm that optimizes the arrangement of cluster heads and base station is developed. On the other hand, based on the Bayesian inference, the uncertainty of the estimated parameters can be quantified. The coefficient of variance of the estimated parameters can be obtained, which is utilized as a holistic measure to evaluate the estimation accuracy of sensor configurations with multi-type of sensors. The proposed method provides the optimal wireless sensor network configuration that satisfies the required estimation accuracy with the longest lifetime. The proposed method is illustrated by designing the optimal wireless sensor network configuration of a cable-stayed bridge and a space truss.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.77-91
• /
• 2022

Various monitoring systems have been implemented in civil infrastructure to ensure structural safety and integrity. In long-term monitoring, these systems generate a large amount of data, where anomalies are not unusual and can pose unique challenges for structural health monitoring applications, such as system identification and damage detection. Therefore, developing efficient techniques is quite essential to recognize the anomalies in monitoring data. In this study, several machine learning techniques are explored and implemented to detect and classify various types of data anomalies. A field dataset, which consists of one month long acceleration data obtained from a long-span cable-stayed bridge in China, is employed to examine the machine learning techniques for automated data anomaly detection. These techniques include the statistic-based pattern recognition network, spectrogram-based convolutional neural network, image-based time history convolutional neural network, image-based time-frequency hybrid convolution neural network (GoogLeNet), and proposed ensemble neural network model. The ensemble model deliberately combines different machine learning models to enhance anomaly classification performance. The results show that all these techniques can successfully detect and classify six types of data anomalies (i.e., missing, minor, outlier, square, trend, drift). Moreover, both image-based time history convolutional neural network and GoogLeNet are further investigated for the capability of autonomous online anomaly classification and found to effectively classify anomalies with decent performance. As seen in comparison with accuracy, the proposed ensemble neural network model outperforms the other three machine learning techniques. This study also evaluates the proposed ensemble neural network model to a blind test dataset. As found in the results, this ensemble model is effective for data anomaly detection and applicable for the signal characteristics changing over time.

• Journal of the Korean Institute of Gas
• /
• v.7 no.3 s.20
• /
• pp.24-31
• /
• 2003

To operate process plant safely and economically, process monitoring is very important. There are a great number of data acquired through distributed control system and process information system. Fault monitoring is the task with difficulties owing to not only the huge amount of data, but also nonlinearity of chemical processes. In this research, the program, REFA, based on PCA and functional link associative neural network has developed. REFA has better learning capabilities, generalization abilities, and shorter learning time than existing neural network programs. In this work its usefulness has proven by application to Tennessee Eastman process.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.50 no.11
• /
• pp.506-513
• /
• 2001

The islanding detection for distributed resources (DR) becomes an important and emerging issue in power system protection since the distributed generator installations are rapidly increasing and most of the installed systems are interconnected with distribution network. In order to avoid the negative impacts from islanding operations of DR on protection, operation and management of distribution system, it is necessary to effectively detect the islanding operations of DR and rapidly disconnect it from distribution network. Generally, it is difficult to detect islanding operation by monitoring only one system parameter This paper presents a new logic based islanding detection method for distributed resources(DR) which are interconnected with distribution network. The proposed method detects the islanding operation by monitoring four system parameter: voltage variation, phase displacement, frequency variation, and the variation of total harmonic distortion(THD) of current; therefore, it effectively detects island operation of DR unit operating in parallel with the distribution network. We also verified the efficiency of the proposed algorithm using the radial distribution network of IEEE 34 bus model.

• Journal of Electrical Engineering and Technology
• /
• v.6 no.6
• /
• pp.776-785
• /
• 2011

Since the Internet-based real-time Global Positioning System(GPS) synchronized widearea power system frequency monitoring network (FNET) was proposed in 2001, it has been monitoring the power system frequency in interconnected United States power systems and numerous interesting behaviors have been observed, including frequency excursion propagation. We address the consistency of a frequency excursion detection order of frequency disturbance recorders in FNET in relation to the same generation trip, as well as the ability to recreate by power systems dynamic simulation. We also propose a new method, as an application of FNET measurement, to locate a tripped generator using power systems dynamic simulation and wide-area frequency measurement. The simulation database of all the possible trips of generators in the interconnected power systems is created using the off-line power systems dynamic simulation. When FNET detects a sudden drop in the monitoring frequency, which is most likely due to a generation trip in power systems, the proposed algorithm locates a tripped generator by finding the best matching case of the measured frequency excursion in the simulation database in terms of the frequency drop detection order and the time of monitoring points.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.3 no.3
• /
• pp.136-142
• /
• 2008

Mobile robots can offer services like intelligent monitoring in an indoor environment using network connection with remote users. In this paper, we designed and developed a networked security robot system with various sensors, such as flame detector, gas detector, sound monitoring module, and temperature sensor, etc. The robot can be accessed through a web service and the user can check the status of the environment. Using ADAMS software, we defined the motor specification for a worst-case condition of climbing over a obstacle. We applied the robot system in monitoring office condition.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2010.07a
• /
• pp.32-35
• /
• 2010

This paper presents an efficient monitoring method of a network protocol for a downloadable conditional access system (DCAS) that can securely transmit conditional access software via a bi-directional communication channel. In order to guarantee a secure channel based on mutual authentication between a DCAS head end server and set-top boxes, DCAS messages are encrypted and digitally signed. Owing to applied cryptographic algorithms, it is impossible to get information from messages directly without additional processing. Through categorizing DCAS messages into several groups, the proposed monitoring method can efficiently parse and trace DCAS messages in real-time. In order to verify the stability and effectiveness of the proposed monitoring method, we implement a DCAS monitoring system capable of capturing and parsing all DCAS messages. The experimental results show that the proposed monitoring method is well designed.

• International Journal of Contents
• /
• v.9 no.4
• /
• pp.22-29
• /
• 2013

In this paper, we propose a integrated real-time monitoring system for recycling agriculture resourcing based on USN. We design and implement the monitoring system so that we can integrate the quality control of farmyard and liquid manures, barn environment monitoring, and positioning information control into a total management system performing recycling of excrement and manure. Selection of sensors and sensor-node construction and requirements, structure of wire/wireless communication networks, and design of monitoring program are also presented. As a result of operating our system, we can get over various drawbacks of conventional separated system and promote the proper circulation of excrement up to the farmyard. We confirm that these advanced effects arise from the effective management of the total system integrating quality control of farmyard/liquid manure, barn/farmhouse information, and vehicle moving monitoring information etc. Moreover, this monitoring system is able to exchange real-time information throughout communication networks so that we can construct a convenient information environment for agricultural community by converging IT technology with farm and stockbreeding industries. Finally we present some results of processing using our monitoring system. Sensing data and their graphs are processed in real-time, positioning information on the v-world map offers various moving paths of vehicles, and statistical analysis shows all the procedure from excrement occurrence to recycling and resourcing.

• Journal of Biomedical Engineering Research
• /
• v.29 no.4
• /
• pp.295-301
• /
• 2008

A wireless 3 channel ECG monitoring system was developed so that it could monitor the health and movement state during subject's daily life. The developed system consists of a wireless biomedical signal acquisition device, a personal healthcare server, and a remote medical server. Three experiments were performed to evaluate the accuracy, reliability and operability, applicability during daily life of the developed device. First, ECG signals were measured using the developed device and commercial reference device during sitting and marking time and compared to verify the accuracy of R-R intervals. Second, the reliable data transmission to remote server was verified on two types of simulated emergency event using patient simulator. Third, during five types of motion in daily life, the accuracy of data transmission to remote server using CDMA network was verified on two types of event occurring. By acquiring and comparing subject's biomedical signal and motion signal, the accuracy, reliability and operability, applicability during daily life of the developed device were verified. In addition, PDA-phone based wireless system enabled subject to be monitored without any constraints. Therefore, the developed system is expected to be applicable for monitoring the aged and chronic diseased people and giving first-aid in emergency.